Training in progress, step 2250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b4d8ec59c75cbd29c1373a150cd6676c15212c5086c6d8411cc0ba90aab5c6
+oid sha256:dc373811286053bff81db740613656f4ba9fe7fdb7e406401d4cb430f04ff3ec
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b9397c2d7a6e54c8bdd82d78a1f67791c66fe1c65a90cafd67110df65ca963
+oid sha256:dc14306598d59f4093a6835603acdc7be8c34d58f259448f089f55239326eef9
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62563564114f07c55d673b83157579ed006c954c798b78b19cdb4e6590a7a7e5
+oid sha256:31a4e7954a06ef587699673e6f8e225350e2c0f70b9309dc051a495886a330f3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8815a24b224041b13ab7cbf09bd12ddf87977f385c87ba515e891819a21f4935
+oid sha256:88b9816dd9ff2c86931b2a1a597995744d96003dfef41dde5f6e6cc74bd8f07f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01772047052826913,
+  "epoch": 0.017919576938699118,
   "eval_steps": 500,
-  "global_step": 2225,
+  "global_step": 2250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2671,6 +2671,42 @@
       "reward_std": 0.2212974861264229,
       "rewards/custom_reward_simplified_v7_dblog": 0.753125,
       "step": 2220
+    },
+    {
+      "completion_length": 695.54375,
+      "epoch": 0.017760291810355128,
+      "grad_norm": 0.27871131896972656,
+      "kl": 0.02111934470012784,
+      "learning_rate": 7.603025030471001e-08,
+      "loss": 0.0008,
+      "reward": 0.75,
+      "reward_std": 0.2767858363687992,
+      "rewards/custom_reward_simplified_v7_dblog": 0.75,
+      "step": 2230
+    },
+    {
+      "completion_length": 632.99375,
+      "epoch": 0.017839934374527123,
+      "grad_norm": 0.008834543637931347,
+      "kl": 0.016428270121105017,
+      "learning_rate": 6.738782355044048e-08,
+      "loss": 0.0007,
+      "reward": 0.80625,
+      "reward_std": 0.21589626967906952,
+      "rewards/custom_reward_simplified_v7_dblog": 0.80625,
+      "step": 2240
+    },
+    {
+      "completion_length": 634.0625,
+      "epoch": 0.017919576938699118,
+      "grad_norm": 0.286683052778244,
+      "kl": 0.016679517249576746,
+      "learning_rate": 5.92599822001666e-08,
+      "loss": 0.0007,
+      "reward": 0.853125,
+      "reward_std": 0.2905955038964748,
+      "rewards/custom_reward_simplified_v7_dblog": 0.853125,
+      "step": 2250
     }
   ],
   "logging_steps": 10,